CoReS: Compatible Representations via Stationarity

11/15/2021
by   Niccolo Biondi, et al.
2

In this paper, we propose a novel method to learn internal feature representation models that are compatible with previously learned ones. Compatible features enable for direct comparison of old and new learned features, allowing them to be used interchangeably over time. This eliminates the need for visual search systems to extract new features for all previously seen images in the gallery-set when sequentially upgrading the representation model. Extracting new features is typically quite expensive or infeasible in the case of very large gallery-sets and/or real time systems (i.e., face-recognition systems, social networks, life-long learning systems, robotics and surveillance systems). Our approach, called Compatible Representations via Stationarity (CoReS), achieves compatibility by encouraging stationarity to the learned representation model without relying on previously learned models. Stationarity allows features' statistical properties not to change under time shift so that the current learned features are inter-operable with the old ones. We evaluate single and sequential multi-model upgrading in growing large-scale training datasets and we show that our method improves the state-of-the-art in achieving compatible features by a large margin. In particular, upgrading ten times with training data taken from CASIA-WebFace and evaluating in Labeled Face in the Wild (LFW), we obtain a 49% increase in measuring the average number of times compatibility is achieved, which is a 544% relative improvement over previous state-of-the-art.

READ FULL TEXT

page 8

page 9

page 12

page 14

research
03/26/2020

Towards Backward-Compatible Representation Learning

We propose a way to learn visual features that are compatible with previ...
research
11/16/2022

CL2R: Compatible Lifelong Learning Representations

In this paper, we propose a method to partially mimic natural intelligen...
research
03/03/2022

Towards Universal Backward-Compatible Representation Learning

Conventional model upgrades for visual search systems require offline re...
research
10/13/2022

Darwinian Model Upgrades: Model Evolving with Selective Compatibility

The traditional model upgrading paradigm for retrieval requires recomput...
research
04/08/2020

Training Neural Networks to Produce Compatible Features

This paper makes a first step towards compatible and hence reusable netw...
research
03/08/2023

FastFill: Efficient Compatible Model Update

In many retrieval systems the original high dimensional data (e.g., imag...
research
08/11/2020

Unified Representation Learning for Cross Model Compatibility

We propose a unified representation learning framework to address the Cr...

Please sign up or login with your details

Forgot password? Click here to reset